Related Experiment Video
Updated: Aug 6, 2026
Mass Spectrometry-Guided Genome Mining as a Tool to Uncover Novel Natural Products
Published on: March 12, 2020
LLM-Assisted Development of a Locally Deployable Molecular Networking Toolkit: Enabling Customizable Analysis in
Shirou Feng1,2, Zihui Yang3,4, Yujun Liu5
1Key Laboratory of Chemical Biology and Traditional Chinese Medicine Research (Ministry of Education), Key Laboratory of Phytochemistry R&D of Hunan Province, and Key Laboratory of the Assembly and Application of Organic Functional Molecules of Hunan Province, Institute of Interdisciplinary Studies, College of Chemistry and Chemical Engineering, Hunan Normal University, Changsha, China, 410081.
Abstract:
MN-Suite is an open-source, locally deployable molecular networking toolkit developed through LLM-assisted software engineering to provide a flexible, server-independent workflow for natural product MS/MS analysis. The toolkit integrates six similarity algorithms and three spectral modes (MS2, neutral loss (NL), and hybrid MS2+NL), offering a customizable GUI-based framework for local preprocessing, network construction, and visualization. In the Aconitum data set examined here, the neutral-loss entropy-similarity strategy (NL-ES) produced the highest internal RCF score among the tested algorithm-data combinations (RCF = 0.537). By combining diagnostic-ion/neutral-loss filtering with a seed-neighborhood strategy, the MN-Suite prioritized 26 putative alkaloid analogues for further structural confirmation. These results support MN-Suite as a practical local workflow for configurable molecular networking and illustrate how domain experts can use LLM-assisted software engineering under human oversight to develop specialized computational tools.
